OrcaRouter Releases Uncensored Weights for Qwen3.8 27B FP8
QuixiAI · x · 2026-08-16
OrcaRouter has released uncensored FP8 weights for the Qwen3.8 27B model. Designed specifically for AI red teaming and security research, this version removes safety filters to help researchers better evaluate model safety boundaries and potential risks.
More from Models
- llama.cpp integrates Dots3 Note model, scoring 78.4 on SWE-bench Verified — victormustar · 2026-08-16
- Post-training boosts GLM-5.3 to rival larger models, showing size isn't the bottleneck — haider1 · 2026-08-16
- Commits suggest Qwen 35B model removed, likely not releasing — Local-Cardiologist-5 · 2026-08-16
- Blind Test: Anime Girl 3D Scene Generation Across Models — Jeanodel · 2026-08-16
- 1-bit Quantized Qwen 27B Runs on 12GB VRAM at 92 tokens/s — zyxciss · 2026-08-16
- BlueBench Cyber Benchmark: GPT-5.6 Sol Leads, Kimi K3 Tops Open-Weights — vijaybolina · 2026-08-16